© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 5694
    Prev
    Next
    INDEX
    Explanations

    use

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     국제
    -0.08
    نج
    -0.07
     Den
    -0.07
     Coleman
    -0.07
    隔着
    -0.07
    𬭩
    -0.07
     Dam
    -0.07
    jące
    -0.07
    基金经理
    -0.07
    .mag
    -0.06
    POSITIVE LOGITS
     disclosures
    0.07
    �
    0.07
    mouseleave
    0.07
    企業
    0.07
    .Type
    0.07
    �
    0.07
    萑
    0.06
     rio
    0.06
    룹
    0.06
    ificate
    0.06
    Activations Density 0.047%

    No Known Activations